Skills de Claude Code · página 129

Problem analysis using Explore agents

Guided 5-minute onboarding for Director Mode Lite

Delegate tasks to Codex CLI to save Claude context

Delegate tasks to Gemini CLI to save Claude context

Generate hook script from template

Validate hooks configuration and scripts

>

Validate MCP configuration and suggest improvements

Create detailed execution plan with task breakdown

Complete project health audit (7 checks)

Expert-guided project setup with 6 phases

Validate skill/command file format and structure

Generate custom skill/command from template

List all available skills (core + custom)

Conventional Commits with quality checks

Test-Driven Development (TDD Red-Green-Refactor)

Test automation specialist for running tests and ensuring coverage

Complete 5-step development workflow

This skill activates for web scraping and Actor development. It proactively discovers APIs via traffic interception, recommends optimal strategy (traffic interception/sitemap/API/DOM scraping/hybrid), and implements iteratively. For production, it guides TypeScript Actor creation via Apify CLI.

Use whenever the user asks to install, configure, uninstall, snooze, mute, test, troubleshoot, or change settings for the echook audio notification system. Trigger phrases include "audio hooks", "audio notifications", "snooze audio", "mute claude", "claude is too loud", "test audio", "switch audio theme", "rate limit alerts", "audio webhook", "TTS", "text to speech", "focus flow", "breathing exercise", "notification mode", "audio only", "notification only", "debounce", "status line", "statusline", "context usage", "context window", "context monitor", "compact reminder", "uninstall audio", "audio status", "audio version", "install for cursor", "install for codex", "codex audio", "codex hooks", "cursor audio", "cursor hooks", and the slash command /audio-hooks. Also use when diagnosing why Claude Code, Cursor, or Codex is silent (or noisy) for the user, or when the user wants to monitor context window usage.

フロントエンドUIデザインを洗練された独自性のあるスタイルで生成します。ランディングページ、ダッシュボード、Webアプリケーションのデザイン、UIコンポーネント作成時に使用してください。「AIっぽい」汎用デザインを避け、プロフェッショナルで記憶に残るUIを実現します。

>

Format markdown and publish to WeChat Official Account via bm.md rendering + WeChat official API

Design RESTful APIs with best practices for consistency and usability

Provides coding assistance with best practices and code review

Systematic debugging approach for identifying and fixing issues

Git best practices for version control and collaboration

Write comprehensive tests following TDD and BDD principles

Create a new skill via GitHub search, LLM generation, or both.

Convert a codebase into a self-contained HTML portal app for ingestion into AI application systems. Produces a single deployable HTML file with embedded CSS, JS, and data.

Create, manage, and chat with Pinecone Assistants for document Q&A with citations. Handles all assistant operations - create, upload, sync, chat, context retrieval, and list. Recognizes natural language like "create an assistant from my docs", "ask my assistant about X", or "upload my docs to Pinecone".

Guide for using the Pinecone CLI (pc) to manage Pinecone resources from the terminal. The CLI supports ALL index types (standard, integrated, sparse) and all vector operations — unlike the MCP which only supports integrated indexes. Use for batch operations, vector management, backups, namespaces, CI/CD automation, and full control over Pinecone resources.

Curated documentation reference for developers building with Pinecone. Contains links to official docs organized by topic and data format references. Use when writing Pinecone code, looking up API parameters, or needing the correct format for vectors or records.

Create, ingest into, and query a Pinecone full-text-search (FTS) index using the preview API (2026-01.alpha, public preview). Use when the user or agent asks to build a text search index on Pinecone, add dense or sparse vector fields, ingest documents, construct score_by clauses (text / query_string / dense_vector / sparse_vector), or compose with text-match filters ($match_phrase / $match_all / $match_any). Ships `scripts/ingest.py` for safe bulk ingestion (batch_upsert + error inspection + readiness polling); query construction is documented inline in this skill — write `documents.search(...)` calls directly, validated against `pc.preview.indexes.describe(...)` output.

Overview of all available Pinecone skills and what a user needs to get started. Invoke when a user asks what skills are available, how to get started with Pinecone, or what they need to set up before using any Pinecone skill.

Reference for the Pinecone MCP server tools. Documents all available tools - list-indexes, describe-index, describe-index-stats, create-index-for-model, upsert-records, search-records, cascading-search, and rerank-documents. Use when an agent needs to understand what Pinecone MCP tools are available, how to use them, or what parameters they accept.

Build n8n workflows using the Pinecone Assistant node or Pinecone Vector Store node. Use when building RAG pipelines, chat-with-docs workflows, configuring Pinecone nodes in n8n, troubleshooting Pinecone n8n nodes, or asking about best practices for Pinecone in n8n.

Query integrated indexes using text with Pinecone MCP. IMPORTANT - This skill ONLY works with integrated indexes (indexes with built-in Pinecone embedding models like multilingual-e5-large). For standard indexes or advanced vector operations, use the CLI skill instead. Requires PINECONE_API_KEY environment variable and Pinecone MCP server to be configured.

Interactive Pinecone quickstart for new developers. Choose between two paths - Database (create an integrated index, upsert data, and query using Pinecone MCP + Python) or Assistant (create a Pinecone Assistant for document Q&A). Use when a user wants to get started with Pinecone for the first time or wants a guided tour of Pinecone's tools.

Fast-path AI visibility — get a brand's 0–100 Akii Visibility Score (computed by an open-source LLM judge against the brand's public footprint) with four-dimension breakdown AND a per-engine proxy map for ChatGPT, Claude, Gemini, Perplexity, Copilot, and Google AI Overviews based on FirstPageSage signal weights. Single-turn fast path. This is the default for any AI-visibility question. Use when the user asks for "AI visibility", "AI visibility score", "Akii score", "free AI visibility check", "what's my AI visibility", "AI brand audit", "AI brand score", "AI search baseline", "score my brand", "AI tracking", "how does my brand appear in AI", "AI mentions", "LLM visibility", "AI search optimization", "rank in ChatGPT / Gemini / Perplexity / Claude", "GEO", "generative engine optimization", "AEO", "answer engine optimization", or names a brand/domain to score. Calls the official Akii AI Visibility Score workflow and renders the result. **Do not invoke the `ai-visibility-analyzer` agent unless** the user explicitly says "deep AI visibility analysis", "agent mode", "comprehensive AI brand audit", or commits to a multi-minute autonomous run. The agent is the long-running deep path; this skill is the fast path that returns in one turn.

Find and fix broken links — three modes with different scale ceilings. `local` audits any local repo (HTML/MD/MDX, no size limit) via Glob/Grep + per-link verification. `page` checks one live URL deeply (~30-100 outbound links per run). `site` requires the Ahrefs site-audit MCP for true multi-page crawl — without it, refuses and tells the user how to get there. Use when the user asks to "check broken links", "find dead links", "fix 404s", "link checker", "broken link audit", "redirect chains", "find dead URLs", "link validation", "mixed content". Accepts a mode modifier (`--mode=local|page|site`); auto-detects from the target if unspecified.

Fast-path competitor intelligence — produces a side-by-side SEO + AEO + GEO + AI visibility scorecard plus ranked counter-move plan. Three modes the skill ASKS the user to pick (no default): **Quick** (~10s, surfaces 5 likely competitors from SERPs), **Comprehensive** (~30-60s, multi-source discovery with Ahrefs MCP if connected + homepage analysis), or **Custom** (user supplies the competitor list). Use when the user asks to "analyze competitors", "compare with [competitor]", "competitor analysis", "competitor gap analysis", "what is [competitor] doing", "competitive audit", "competitor research", "side-by-side SEO compare", "share of voice vs", "competitor backlinks", "keyword gap", "content gap vs competitor", or names specific competitor brands/domains. **Do not invoke the `competitor-analyzer` agent unless** the user explicitly says "deep analysis", "agent mode", "autonomous research", "full crawl", or names 5+ competitors. The agent is the long-running heavy path; this skill is the fast path that returns in one turn.

Generate a detailed content brief for a specific article or page. Use when the user asks to "create a content brief", "write a brief", "article outline", "blog brief", "writing brief", "content outline", "SEO brief", "AEO brief", "GEO brief", or wants a structured plan before writing.

Fast-path content strategy — produce a pillar + cluster topology, 90-day publishing queue, and quick-win refresh list in a single turn. This is the default for any content-planning question. Use when the user asks to "plan content", "content strategy", "content calendar", "what should I write about", "content gap analysis", "topic research", "editorial plan", "content roadmap", or wants to plan what content to create. **Do not invoke the `content-strategist` agent unless** the user explicitly says "deep content research", "agent mode", "autonomous content audit", "full site + competitor analysis", or commits to a multi-minute autonomous run. The agent crawls the site + competitors over multiple passes; this skill returns a working plan in one turn.

Translate and localize content for international SEO. Use when the user asks to "translate content", "localize my site", "multilingual SEO", "translate to <language>", "international SEO", "hreflang", "multi-language website", "global content strategy", or wants to expand to new markets.

Analyze and improve internal linking strategy. Use when the user asks about "internal links", "link structure", "site architecture", "link strategy", "orphan pages", "link equity", "page authority distribution", "anchor text", "topical clusters", "siloing", or wants to improve how pages connect.

Cluster and organize keywords into topical groups for SEO. Use when the user asks to "cluster keywords", "group keywords", "organize keywords", "keyword mapping", "topic clusters", "keyword grouping", "build a content plan", "pillar pages", "topical authority", "semantic clustering", or pastes a list of keywords.

Generate and maintain llms.txt and llms-full.txt — the emerging standard telling LLM-powered crawlers what content matters most on your site. Use when the user asks "llms.txt", "llms-full.txt", "LLM-friendly file", "tell AI crawlers about my site", "AI-readable manifest", "site summary for LLMs", "llms file", "generative AI sitemap", or wants their site optimized for AI crawler ingestion.

Comprehensive single-page optimization across all three layers — traditional SEO (title / meta / H1 / internal links), AEO (chunk quality, direct-answer leads, FAQ extraction), and GEO rewrites using the tactics published by the Princeton/IIT Delhi GEO study (citation integration, expert quotes, statistics enrichment, fluency optimization, authoritative tone). Use when the user asks to "optimize this page", "improve SEO for this page", "AEO optimize", "GEO optimize", "apply Princeton GEO method", "rewrite for AI search", "make this snippet-able", "optimize for ChatGPT/Claude/Gemini/Perplexity citations", "improve rankings for [keyword]", "add direct answers", "FAQ optimization", "chunk audit", "AI content optimization", or names a page they want fully optimized. Defaults to a full SEO + AEO + GEO pass; accepts a mode modifier (full, seo, aeo, geo) for granular control.

Fast-path schema generator — produce, audit, and validate JSON-LD structured data for a single page or file in one turn. This is the default for any schema question. Use when the user asks to "generate schema", "add JSON-LD", "structured data", "schema markup", "rich snippets", "add schema.org", "LocalBusiness schema", "FAQ schema", "Product schema", "Article schema", "HowTo schema", "Organization schema", "BreadcrumbList schema", "audit schema", "fix schema errors", "Recipe schema". **Do not invoke the `schema-generator` agent unless** the user explicitly says "bulk schema", "across my site", "all pages", "every page", or names a path containing 3+ pages to fix. The agent is the autonomous multi-file path that writes into source; this skill is the one-page fast path that proposes JSON-LD inline.

Single audit entry point — surface-level scorecard or deep infrastructure dive depending on the requested mode. Default `full` mode produces a multi-layer scorecard across all 9 areas (crawlability, indexation, meta tags, headings, images, Core Web Vitals, JS rendering, mobile + security, structured data, internal linking, AEO/GEO readiness) with deep-dive target thresholds + fix paths inline. `quick` mode = scorecard only, surface-level pass/fail. `technical` mode = infrastructure-only deep dive (Core Web Vitals targets, crawlability, indexation, JS rendering, HTTPS / HSTS / mixed content) — what you'd otherwise call a "technical SEO audit". Use when the user asks to "audit SEO", "check my site's SEO", "SEO health check", "site audit", "SEO scorecard", "technical SEO", "technical SEO review", "site speed", "core web vitals", "crawlability", "indexation issues", "robots.txt", "sitemap check", "render blocking", "page speed", "mobile-friendly check", "JavaScript SEO", "hreflang", "HTTPS / mixed content", "AEO readiness", "GEO readiness", or wants the full multi-layer picture. Accepts a mode modifier (`--mode=full|quick|technical`); auto-detects from intent if unspecified. **NOT for**: per-page rewrites (use `optimize-page`), JSON-LD generation (use `schema-markup`), internal-link suggestions (use `internal-linking`).

Reads production/traces/agent-metrics.jsonl and displays a per-agent performance summary table for the current or a specified session. Highlights agents with high error rates or OPEN circuit breaker state.

Provides the vendored agent-style v0.3.5 prose rule pack as a portable Claude skill. Use when installing, syncing, applying, or auditing SDD Agent-Style support in another project, or when a style-review workflow needs the bundled rules.

Provides Angular best practices for components, modules, services, and reactive patterns. Use when working with Angular TypeScript files, component templates, NgModules, RxJS observables, or when the user mentions Angular, ng, or Angular CLI.

Records unexpected API behaviors, undocumented caveats, version bugs, or non-obvious workarounds into .claude/memory/annotations.md. Use immediately when an undocumented behavior or surprising caveat is discovered during development.

Defines REST and GraphQL API contracts including endpoints, request/response schemas, auth flows, and versioning strategy. Use when designing a new API, reviewing an API spec, or when the user mentions API design, OpenAPI, or endpoint contracts.

Manages the ADR (Architecture Decision Record) registry. Use when recording tech-stack choices, design patterns, or infrastructure decisions with context, alternatives, and rationale. Supports listing, searching, or creating formal ADR documents.

Provides AWS serverless architecture patterns for Lambda, API Gateway, DynamoDB, SQS, and SAM/CDK. Use when working with AWS serverless files (serverless.yml, CDK stacks) or when the user mentions Lambda, API Gateway, serverless, or AWS SAM.

Designs scalable backend architectures covering microservices, event-driven systems, API gateways, and data stores. Use when designing a backend system or when the user mentions backend architecture, scalability, or distributed systems.

Applies production backend patterns: middleware, error handling, auth, database integration, and API design. Use when working with backend service files or when the user mentions Express, Fastify, NestJS, backend patterns, or service architecture.

Facilitates structured product ideation to define user needs, core value, and product direction. Use when the user wants to explore a new product idea, has a vague concept to develop, or mentions brainstorming or ideation.

Creates a structured bug report with reproduction steps, expected vs actual behavior, environment details, and severity assessment. Use when a bug or defect is found and needs to be formally documented.

Provides code patterns for the Anthropic Claude API including streaming, tool use, and prompt caching. Use when working with Anthropic SDK files or when the user mentions Claude API, Anthropic client, or LLM integration.

Designs multi-cloud and hybrid cloud architectures across AWS, GCP, and Azure. Use when designing cloud infrastructure or when the user mentions cloud architecture, AWS, GCP, Azure, or multi-cloud.

Deploys Puppeteer browser automation on Google Cloud Run with Docker. Use when running headless browser tasks on Cloud Run, or when the user mentions Cloud Run, Puppeteer, headless Chrome, or serverless browser automation.

Provides a comprehensive code review checklist for pull requests covering security, performance, maintainability, and testing. Use as a reference during code reviews or when the user asks for a review checklist.

Performs architectural and quality code review checking coding standards, SOLID principles, architectural compliance, and common software issues. Use when reviewing a file or directory before merge, or when the user mentions code review, PR review, or quality check.

Simplifies working code while preserving exact behavior. Use after tests pass, during review feedback, or when code is harder to read, maintain, or verify than it needs to be without changing product behavior.

Adapts SDD for Codex while preserving Claude Code behavior. Use when working in Codex, setting up Codex compatibility, mapping Claude tools to Codex tools, or explaining how SDD should run outside Claude Code.

Creates a well-formed git commit following conventional commit format with type, scope, and descriptive message. Use when the user is ready to commit changes or mentions conventional commits.

Strictly enforce context engineering principles to avoid context stuffing, optimize memory architecture, and manage the Research-Plan-Reset-Implement cycle.

Designs relational and NoSQL database schemas, indexing strategies, migration plans, and data modeling patterns. Use when designing a database or when the user mentions database architecture, schema design, or data modeling.

Reviews database schemas, queries, and migrations for correctness, performance, security, and best practices. Use when reviewing SQL migration files or when the user mentions database review, schema review, or query audit.

Conducts a structured technical deep-dive to gather detailed requirements, constraints, and decisions from the user. Use when starting a complex feature or when the user wants to be asked structured clarifying questions before implementation.

Reviews UI/UX designs, wireframes, and design systems for usability, accessibility, consistency, and implementation feasibility. Use when reviewing design specs or when the user mentions design review, UX review, or design feedback.

Decomposes a product concept into architectural components, domain systems, data models, and integration boundaries. Use when starting system architecture or when the user mentions system design or component breakdown.

Designs and executes CI/CD pipelines, GitOps workflows, deployment automation, and cloud infrastructure deployment including Docker, AWS Lambda, SAM, Terraform, and GitHub Actions. Use when building or improving CI/CD pipelines, containerizing applications, creating deployment runbooks, or deploying to cloud infrastructure.

Diagnostic pipeline for complex/intermittent bugs. Uses diagnostics roles for Investigation, Verification, and Solution before Lead Programmer handoff. Use ONLY for non-obvious failures (root cause unclear, reproduction unstable, fixes reverted). NOT for trivial bugs with known cause — fix them directly.

Provides expert-level Django development patterns covering App Router (indirectly via REST/GraphQL), async views, DRF, Celery, signals, middleware, and performance optimization. Use when building complex Django 5.x applications or identifying N+1 query issues.

Provides Docker and Docker Compose patterns including multi-stage builds, networking, volumes, and production configurations. Use when working with Dockerfile or docker-compose.yml, or when the user mentions Docker, containers, or containerization.

Provides .NET and ASP.NET Core patterns for REST APIs, Entity Framework, dependency injection, and middleware. Use when working with C# files (*.cs, *.csproj) or when the user mentions .NET, ASP.NET Core, C#, or Entity Framework.

Consolidates and prunes the memory directory through a 4-phase reflective pass: Orient, Gather, Consolidate, Prune. Run after intensive sessions, when memories feel duplicated, or when MEMORY.md approaches the 200-line limit.

Provides Drizzle ORM schema design, query patterns, migrations, and TypeScript integration for SQL databases. Use when working with Drizzle files (schema.ts, drizzle.config.ts) or when the user mentions Drizzle ORM or drizzle-kit.

Produces time and complexity estimates for features, tasks, or sprints using story points, t-shirt sizing, or day estimates. Use when the user asks for an estimate, wants to size a feature, or mentions estimation or planning poker.

Designs event-sourced systems with CQRS, event stores, projections, and eventual consistency patterns. Use when architecting event-driven systems or when the user mentions event sourcing, CQRS, event store, or domain events.

Production FastAPI patterns — async endpoints, SQLAlchemy 2.0 async, Pydantic V2, dependency injection, JWT auth, testing. Use for Python 3.11+ FastAPI backends. NOT for Django (→ `django-patterns`) or Node.js (→ `backend-patterns`).

Runs multiple specialist subagents in parallel then merges their outputs into a unified result. Use when a task can be split into independent parallel workstreams that need to be recombined.

Locks the codebase to prevent unintended writes during a freeze period such as before a release or during an incident. Use when the user mentions freezing, code lock, or release lockdown.

Designs frontend UI architecture including component hierarchy, state management strategy, design tokens, and accessibility requirements. Use when starting frontend design or when the user mentions UI architecture, component design, or frontend planning.

Framework-agnostic React/Vue patterns — component composition, hooks, TanStack Query, memoization, error boundaries. Use for generic React/Vue work (Vite, CRA, Storybook). For Next.js App Router / Server Components specifically, use `senior-frontend` instead.

Builds dark-themed TypeScript UIs with accessible color systems, contrast compliance, and responsive design patterns. Use when implementing dark mode or building accessible TypeScript UI components.

Validates a software product, service, or feature against readiness gates before advancing to the next delivery phase. Use when planning a phase transition or when the user mentions gate check, phase review, or readiness validation.

Provides code patterns for Google Gemini API integration including text generation, multimodal inputs, and streaming. Use when working with Google AI SDK or when the user mentions Gemini API, Google AI, or Vertex AI.

Provides GitLab CI/CD pipeline patterns including stages, jobs, artifacts, caching, and environment deployments. Use when working with .gitlab-ci.yml or when the user mentions GitLab CI or GitLab pipelines.

Enforces project safety constraints by blocking risky operations outside their approved scope during active development. Use when activating a safety guard or constraint for the current session.

Generates the lightweight 3-field handoff summary for cross-domain work and optionally persists a formal handoff artifact for High-risk transfers.

Executes a hotfix workflow: creates a hotfix branch, applies the targeted fix, runs verification, and prepares release artifacts. Use when a critical production bug needs immediate patching or when the user mentions hotfix or emergency fix.

Designs hybrid cloud architectures connecting on-premises infrastructure with public cloud services. Use when designing systems spanning on-prem and cloud, or when the user mentions hybrid cloud or multi-environment architecture.

Designs Kubernetes deployments, services, ingress, RBAC, Helm charts, and cluster architecture. Use when working with Kubernetes YAML files or when the user mentions Kubernetes, K8s, Helm, or container orchestration.

Provides Laravel PHP patterns for Eloquent ORM, Artisan commands, queues, middleware, and API resources. Use when working with PHP Laravel files (*.php) or when the user mentions Laravel, Eloquent, or PHP framework.